mcp_engram_export

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It describes the behavior as serialization (likely non-destructive) and mentions profile restrictions and degraded geometry. It does not explicitly confirm read-only or disclose any side effects, but the word 'serializes' implies no mutation. Some missing details on concurrency or resource impact, but adequate for the given context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, uses clear labels (BEHAVIOR, USAGE, OUTPUT), and front-loads the main action. Every sentence adds value, and the structure aids quick comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description explicitly states the output format (JSON array with concept, text, crs and degraded geometry). It also covers profile restrictions and filtering. For a simple export tool with one optional parameter, this is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter, min_crs, is fully described in the input schema with default and meaning. The description merely echoes 'filtered by minimum CRS' without adding new semantics. Since schema coverage is 100%, baseline is 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool serializes the active memory manifold into a portable JSON array, with optional filtering by minimum CRS. It distinguishes itself from the sibling mcp_engram_scrub_export by noting the export is block-isomorphic and training-safe for that sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says the tool is blocked in ENGRAM_PROFILE=agent and recommends using mcp_engram_scrub_export instead. It also limits usage to backup/migrate in deep|dev|ui profiles, providing clear when-to-use and when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.